Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5728 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.7391. Min Act: -0.0000

Data Index: 466737 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.7107. Min Act: -0.0000

Data Index: 752126 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6287. Min Act: -0.0000

Data Index: 341536 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6324. Min Act: -0.0000

Data Index: 130102 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.5901. Min Act: -0.0000

Data Index: 533583 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.5864. Min Act: -0.0000

Data Index: 106156 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6234. Min Act: -0.0000

Data Index: 1272403 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6099. Min Act: -0.0000

Data Index: 849847 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.5813. Min Act: -0.0000

Data Index: 726913 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.5967. Min Act: -0.0000

Data Index: 340001 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.5722. Min Act: -0.0000

Data Index: 527587 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.5743. Min Act: -0.0000

Data Index: 874850 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.5516. Min Act: -0.0000

Data Index: 502658 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.5329. Min Act: -0.0000

Data Index: 1231863 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.5631. Min Act: -0.0000

Data Index: 424474 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.5278. Min Act: -0.0000

Data Index: 1245368 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.5472. Min Act: -0.0000

Data Index: 834658 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.5269. Min Act: -0.0000

Data Index: 1170654 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.5589. Min Act: -0.0000

Data Index: 822448 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.5384. Min Act: -0.0000

Data Index: 807220 (C4 (Web Text))

Max Activating Token Index: 950